adextract
Ad libraries are public but fragmented. Every platform is a silo - different UI, different filters, different quirks. If you want to see what competitors are running, you're either opening four tabs and pasting into Excel, or maintaining scrapers that rot with every layout change. adextract gives AI agents a single MCP endpoint to search, read, and compare ads across Meta, TikTok, LinkedIn, and mo
README
Adextract MCP Server
Connect AI assistants to Adextract — search ad libraries across Meta, Google Ads, LinkedIn, and TikTok, plus creative analysis with ad_reader.
Hosted endpoint: https://mcp.adextract.co/mcp
Installation
Hosted MCP (recommended)
Connect to the Adextract hosted server:
https://mcp.adextract.co/mcp
Get your API key at adextract.co (account → API keys).
Cursor
Add to ~/.cursor/mcp.json or project .cursor/mcp.json:
{
"mcpServers": {
"ad-extract": {
"url": "https://mcp.adextract.co/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}
VS Code
Add to .vscode/mcp.json:
{
"servers": {
"ad-extract": {
"type": "http",
"url": "https://mcp.adextract.co/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}
Claude Web (OAuth)
- Open Claude → Settings → Connectors → Add custom connector
- Name:
ad-extract - URL:
https://mcp.adextract.co/mcp - Sign in and approve when prompted — no API key in the URL.
Claude Desktop (mcp-remote)
{
"mcpServers": {
"ad-extract": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.adextract.co/mcp",
"--header",
"Authorization: Bearer YOUR_API_KEY"
]
}
}
}
More clients and config paths: docs/CLIENT_SETUP.md
Available Tools
| Tool | Platform | Description |
|---|---|---|
search_meta_ads |
Meta | Search Facebook & Instagram ads |
search_meta_pages |
Meta | Discover pages and location IDs |
get_meta_page_info |
Meta | Page transparency and metadata |
get_meta_ad_details |
Meta | EU/UK ad transparency details |
search_google_ads |
Google Ads Transparency Center | |
search_google_ads_advertisers |
Advertiser and domain search | |
get_google_ad_details |
Creative details | |
get_google_ads_advertiser_info |
Advertiser profile from Search ads | |
search_linkedin_ads |
LinkedIn Ad Library | |
search_tiktok_ads |
TikTok | TikTok Ads Library |
search_tiktok_advertisers |
TikTok | TikTok advertiser discovery |
get_tiktok_ad_details |
TikTok | Targeting and creative details |
ad_reader |
All | Analyze image/video creatives (format, audience, emotion, archetypes) |
Full reference: docs/TOOLS.md
Prompts & Resources
Built-in MCP prompts for common workflows:
adextract_top_ads_for_brandadextract_competitor_benchmarkadextract_channel_strategyadextract_analyze_ad_urladextract_schedule_watchlist
Resources include agent skill instructions and prompt-pack references (adextract://skill/main, etc.).
Authentication
| Method | Best for |
|---|---|
| OAuth 2.0 | Claude Web and OAuth-capable connectors |
| Bearer API key | Cursor, VS Code, Claude Desktop, mcp-remote |
Discovery endpoints:
https://mcp.adextract.co/.well-known/oauth-protected-resourcehttps://mcp.adextract.co/oauth/.well-known/oauth-authorization-server
Server card (registry / client discovery):
https://mcp.adextract.co/.well-known/mcp.json
Example prompts
Show me the latest Nike ads on Facebook in the US.
→ search_meta_ads({ q: "nike", country: "US", active_status: "active" })
Find Google ads for tesla.com from the last 30 days.
→ search_google_ads({ domain: "tesla.com", time_period: "last_30_days" })
Analyze this ad creative URL with ad_reader.
→ ad_reader({ url: "https://..." })
Documentation
| Doc | Purpose |
|---|---|
| docs/CLIENT_SETUP.md | Per-client configuration |
| docs/TOOLS.md | Tools, prompts, resources |
| docs/TROUBLESHOOTING.md | Common errors and fixes |
| REGISTRY_CHECKLIST.md | Pre-submission checklist |
| SECURITY.md | Security policy |
| SUPPORT.md | How to get help |
Links
- Website: adextract.co
- MCP endpoint:
https://mcp.adextract.co/mcp - Repository: github.com/ad-vertly/adextract-mcp-server
Built with ❤️ by Adextract
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.